Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

2024/02/05 by Qingyuan Wu, Simon Sinong Zhan, Wu, Qingyuan +12 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2402.03141

openalex publication_date 2024/02/05 · openalex created_date 2024/02/08 · openalex updated_date 2026/07/28

Abstract

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

Cited by

• Model-Based Reinforcement Learning under Random Observation Delays
• Reinforcement Learning via Conservative Agent for Environments with Random Delays

Related

• Delays in Reinforcement Learning
• Variational Delayed Policy Optimization
• Reinforcement Learning with Random Delays
• Reinforcement Learning via Conservative Agent for Environments with Random Delays
• DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays